promote-panic_v3.patch

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index dcfef36591..d86137ae8b 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -821,8 +821,14 @@ static XLogSource XLogReceiptSource = 0;	/* XLOG_FROM_* code */
 static XLogRecPtr ReadRecPtr;	/* start of last record read */
 static XLogRecPtr EndRecPtr;	/* end+1 of last record read */
 
-static XLogRecPtr minRecoveryPoint; /* local copy of
-									 * ControlFile->minRecoveryPoint */
+/*
+ * Local copies of equivalent fields in the control file.  When running
+ * crash recovery, minRecoveryPoint is set to InvalidXLogRecPtr as we
+ * expect to replay all the WAL available, and updateMinRecoveryPoint is
+ * switched to false to prevent any updates while replaying records.
+ * Those values are kept consistent as long as crash recovery runs.
+ */
+static XLogRecPtr minRecoveryPoint;
 static TimeLineID minRecoveryPointTLI;
 static bool updateMinRecoveryPoint = true;
 
@@ -2707,7 +2713,7 @@ XLogGetReplicationSlotMinimumLSN(void)
 static void
 UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force)
 {
-	/* Quick check using our local copy of the variable */
+	/* Check using our local copy of minRecoveryPoint */
 	if (!updateMinRecoveryPoint || (!force && lsn <= minRecoveryPoint))
 		return;
 
@@ -2717,14 +2723,7 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force)
 	minRecoveryPoint = ControlFile->minRecoveryPoint;
 	minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
 
-	/*
-	 * An invalid minRecoveryPoint means that we need to recover all the WAL,
-	 * i.e., we're doing crash recovery.  We never modify the control file's
-	 * value in that case, so we can short-circuit future checks here too.
-	 */
-	if (minRecoveryPoint == 0)
-		updateMinRecoveryPoint = false;
-	else if (force || minRecoveryPoint < lsn)
+	if (force || minRecoveryPoint < lsn)
 	{
 		XLogRecPtr	newMinRecoveryPoint;
 		TimeLineID	newMinRecoveryPointTLI;
@@ -3110,7 +3109,7 @@ XLogNeedsFlush(XLogRecPtr record)
 	 */
 	if (RecoveryInProgress())
 	{
-		/* Quick exit if already known updated */
+		/* Quick exit if already known to be updated or cannot be updated */
 		if (record <= minRecoveryPoint || !updateMinRecoveryPoint)
 			return false;
 
@@ -3124,20 +3123,8 @@ XLogNeedsFlush(XLogRecPtr record)
 		minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
 		LWLockRelease(ControlFileLock);
 
-		/*
-		 * An invalid minRecoveryPoint means that we need to recover all the
-		 * WAL, i.e., we're doing crash recovery.  We never modify the control
-		 * file's value in that case, so we can short-circuit future checks
-		 * here too.
-		 */
-		if (minRecoveryPoint == 0)
-			updateMinRecoveryPoint = false;
-
 		/* check again */
-		if (record <= minRecoveryPoint || !updateMinRecoveryPoint)
-			return false;
-		else
-			return true;
+		return record > minRecoveryPoint;
 	}
 
 	/* Quick exit if already known flushed */
@@ -4269,6 +4256,12 @@ ReadRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, int emode,
 				minRecoveryPoint = ControlFile->minRecoveryPoint;
 				minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
 
+				/*
+				 * The startup process can update its local copy of
+				 * minRecoveryPoint from this point.
+				 */
+				updateMinRecoveryPoint = true;
+
 				UpdateControlFile();
 				LWLockRelease(ControlFileLock);
 
@@ -6892,9 +6885,31 @@ StartupXLOG(void)
 		/* No need to hold ControlFileLock yet, we aren't up far enough */
 		UpdateControlFile();
 
-		/* initialize our local copy of minRecoveryPoint */
-		minRecoveryPoint = ControlFile->minRecoveryPoint;
-		minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
+		/*
+		 * Initialize our local copy of minRecoveryPoint.  When doing crash
+		 * recovery we want to replay up to the end of WAL.  Particularly, in
+		 * the case of a promoted standby minRecoveryPoint value in the
+		 * control file is only updated after the first checkpoint.  However,
+		 * if the instance crashes before the first post-recovery checkpoint
+		 * is completed then recovery will use a stale location causing the
+		 * startup process to think that there are still invalid page
+		 * references when checking for data consistency.
+		 */
+		if (InArchiveRecovery)
+		{
+			minRecoveryPoint = ControlFile->minRecoveryPoint;
+			minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
+		}
+		else
+		{
+			/*
+			 * We are to run crash recovery. We shouldn't update
+			 * minRecoveryPoint until crash recvoery ends.
+			 */
+			updateMinRecoveryPoint = false;
+			minRecoveryPoint = InvalidXLogRecPtr;
+			minRecoveryPointTLI = 0;
+		}
 
 		/*
 		 * Reset pgstat data, because it may be invalid after recovery.
@@ -7861,6 +7876,8 @@ CheckRecoveryConsistency(void)
 	if (XLogRecPtrIsInvalid(minRecoveryPoint))
 		return;
 
+	Assert(InArchiveRecovery);
+
 	/*
 	 * assume that we are called in the startup process, and hence don't need
 	 * a lock to read lastReplayedEndRecPtr
@@ -9949,11 +9966,16 @@ xlog_redo(XLogReaderState *record)
 		 * Update minRecoveryPoint to ensure that if recovery is aborted, we
 		 * recover back up to this point before allowing hot standby again.
 		 * This is important if the max_* settings are decreased, to ensure
-		 * you don't run queries against the WAL preceding the change.
+		 * you don't run queries against the WAL preceding the change. The
+		 * local copies cannot be updated as long as crash recovery is
+		 * happening and we expect all the WAL to be replayed.
 		 */
-		minRecoveryPoint = ControlFile->minRecoveryPoint;
-		minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
-		if (minRecoveryPoint != 0 && minRecoveryPoint < lsn)
+		if (InArchiveRecovery)
+		{
+			minRecoveryPoint = ControlFile->minRecoveryPoint;
+			minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
+		}
+		if (minRecoveryPoint != InvalidXLogRecPtr && minRecoveryPoint < lsn)
 		{
 			ControlFile->minRecoveryPoint = lsn;
 			ControlFile->minRecoveryPointTLI = ThisTimeLineID;